utf8.c revision b26fa1a2fbcfee7d03b0c8fd15ec3aa64ae70b9f
/***
This file is part of systemd.
Copyright 2008-2011 Kay Sievers
Copyright 2012 Lennart Poettering
under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1 of the License, or
(at your option) any later version.
systemd is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with systemd; If not, see <http://www.gnu.org/licenses/>.
***/
/* Parts of this file are based on the GLIB utf8 validation functions. The
* original license text follows. */
/* gutf8.c - Operations on UTF-8 strings.
*
* Copyright (C) 1999 Tom Tromey
* Copyright (C) 2000 Red Hat, Inc.
*
* modify it under the terms of the GNU Library General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Library General Public License for more details.
*
* You should have received a copy of the GNU Library General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include <errno.h>
#include <stdbool.h>
#include <stdlib.h>
#include <string.h>
#include "alloc-util.h"
#include "hexdecoct.h"
#include "macro.h"
#include "utf8.h"
return false;
return false;
return false;
return false;
return true;
}
/*
0 to ' '-1 is the C0 range.
DEL=0x7F, and DEL+1 to 0x9F is C1 range.
'\t' is in C0 range, but more or less harmless and commonly used.
*/
}
/* count of characters used to encode one unicode char */
static int utf8_encoded_expected_len(const char *str) {
unsigned char c;
c = (unsigned char) str[0];
if (c < 0x80)
return 1;
if ((c & 0xe0) == 0xc0)
return 2;
if ((c & 0xf0) == 0xe0)
return 3;
if ((c & 0xf8) == 0xf0)
return 4;
if ((c & 0xfc) == 0xf8)
return 5;
if ((c & 0xfe) == 0xfc)
return 6;
return 0;
}
/* decode one unicode char */
int len, i;
switch (len) {
case 1:
return 0;
case 2:
break;
case 3:
break;
case 4:
break;
case 5:
break;
case 6:
break;
default:
return -EINVAL;
}
for (i = 1; i < len; i++) {
return -EINVAL;
unichar <<= 6;
}
*ret_unichar = unichar;
return 0;
}
const char *p;
int encoded_len, r;
if (encoded_len < 0 ||
return false;
r = utf8_encoded_to_unichar(p, &val);
if (r < 0 ||
return false;
length -= encoded_len;
p += encoded_len;
}
return true;
}
const char *utf8_is_valid(const char *str) {
const uint8_t *p;
int len;
len = utf8_encoded_valid_unichar((const char *)p);
if (len < 0)
return NULL;
p += len;
}
return str;
}
char *utf8_escape_invalid(const char *str) {
char *p, *s;
if (!p)
return NULL;
while (*str) {
int len;
if (len > 0) {
} else {
s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
str += 1;
}
}
*s = '\0';
return p;
}
char *utf8_escape_non_printable(const char *str) {
char *p, *s;
if (!p)
return NULL;
while (*str) {
int len;
if (len > 0) {
} else {
while (len > 0) {
*(s++) = '\\';
*(s++) = 'x';
str += 1;
len --;
}
}
} else {
s = stpcpy(s, UTF8_REPLACEMENT_CHARACTER);
str += 1;
}
}
*s = '\0';
return p;
}
char *ascii_is_valid(const char *str) {
const char *p;
for (p = str; *p; p++)
if ((unsigned char) *p >= 128)
return NULL;
return (char*) str;
}
/**
* utf8_encode_unichar() - Encode single UCS-4 character as UTF-8
* @out_utf8: output buffer of at least 4 bytes or NULL
* @g: UCS-4 character to encode
*
* This encodes a single UCS-4 character as UTF-8 and writes it into @out_utf8.
* The length of the character is returned. It is not zero-terminated! If the
* output buffer is NULL, only the length is returned.
*
* Returns: The length in bytes that the UTF-8 representation does or would
* occupy.
*/
if (g < (1 << 7)) {
if (out_utf8)
out_utf8[0] = g & 0x7f;
return 1;
} else if (g < (1 << 11)) {
if (out_utf8) {
}
return 2;
} else if (g < (1 << 16)) {
if (out_utf8) {
}
return 3;
} else if (g < (1 << 21)) {
if (out_utf8) {
}
return 4;
}
return 0;
}
const uint8_t *f;
char *r, *t;
if (!r)
return NULL;
f = s;
t = r;
/* see RFC 2781 section 2.2 */
f += 2;
if (!utf16_is_surrogate(w1)) {
t += utf8_encode_unichar(t, w1);
continue;
}
continue;
break;
f += 2;
if (!utf16_is_trailing_surrogate(w2)) {
f -= 2;
continue;
}
}
*t = 0;
return r;
}
/* expected size used to encode one unicode char */
if (unichar < 0x80)
return 1;
if (unichar < 0x800)
return 2;
if (unichar < 0x10000)
return 3;
if (unichar < 0x200000)
return 4;
if (unichar < 0x4000000)
return 5;
return 6;
}
/* validate one encoded unicode char and return its length */
int utf8_encoded_valid_unichar(const char *str) {
int len, i, r;
if (len == 0)
return -EINVAL;
/* ascii is valid */
if (len == 1)
return 1;
/* check if expected encoded chars are available */
for (i = 0; i < len; i++)
return -EINVAL;
if (r < 0)
return r;
/* check if encoded length matches encoded value */
return -EINVAL;
/* check if value has valid range */
if (!unichar_is_valid(unichar))
return -EINVAL;
return len;
}